HKGAI OfficeAI WORK COMPANIONWeb · EN / 中文

A first task.
A reason to trust.

Helping employees begin, decide what to delegate,
and teach an agent how their work gets done.

Explore the experience ↘
FROM “WHAT DO I ASK?” TO “I CAN HAND THIS OVER”

Your work.
A place to begin.

A prairie dog stands ready with a task slip
MY ROLE

Product strategy & experience

Positioning, task flows, visual identity & mascot
CONTEXT

HKGAI · Government work

Designed for Hong Kong government staff
STAGE

Design & interactive prototype

Sample data · Validation planned
THE PROJECT

With WorkBuddy and other work agents already available, HKGAI Office needs a clear reason to exist. My starting point is the employee using an agent for the first time: they may not know what to ask, which parts of their job to hand over, or how to help the agent understand their way of working. The design explores a path from one useful, reviewable task to a repeatable workflow. That is the differentiation hypothesis this project still needs to prove.

01 / THE PRODUCT QUESTIONFIND A REASON TO BE CHOSEN

Why another agent,
when WorkBuddy already exists?

A new product has to earn a place in someone’s workday. My hypothesis is that first-time employees need help making the first handoff: choosing a worthwhile task, understanding the boundaries, and seeing an outcome they can judge.

THE DIFFERENTIATION TO TEST

Make the first useful handoff easier.
Make the next one more familiar.

For Hong Kong government staff, the opportunity may be in the fit with their tasks, language, documents and review practices. Whether that fit is better than the tools they already use remains an open question.
01 / START

“Where do I begin?”

An empty “Ask agent” box asks a newcomer to invent a use case and explain it. The first design problem is helping them recognize a useful task from their own day.

02 / TRUST

“What can I hand over?”

Employees need to decide which parts of a job the agent can prepare, what they must check, and which actions still need their approval. Trust has to be earned through that experience.

03 / ADAPT

“Will it learn my way?”

Useful work depends on a person’s tone, terminology, source documents and approval steps. A repeat task should benefit from what the employee explicitly teaches and corrects.

These are product questions and design hypotheses, not findings from completed user research or claims about competitors’ limitations.

BUSINESS & DELIVERY CONSTRAINTS

What has to be true for a first release?

The brief sets a product direction, not a confirmed launch plan. These dependencies shape what I can design now, what the team must decide, and what a pilot needs to prove.

VALUE BEFORE BREADTH

Earn a place in an existing workday

Employees already have tools and routines. More capabilities do not establish a reason to switch. I would start with a task people choose and repeat before widening the product.

Decision to validate: which role and first task offer enough value to justify setup and review?
INTEGRATIONS BEFORE PROMISES

A demo is not an operational service

Email, meeting and knowledge connections are simulated. A usable pilot depends on engineering capacity and real backend integration. The prototype makes the handoffs visible while those dependencies remain open.

Pending in the brief: assign integration resources and confirm the first supported sources.
OWNERSHIP BEFORE ROLLOUT

Data commitments need named owners

Storage location, retention and training use are unresolved in the brief. Product, legal and IT owners need to confirm the operating arrangement before the interface can promise it.

Design response: show source scope and approval boundaries; avoid unverified data-residency claims.
A PILOT BEFORE A BUSINESS CASE

Prove repeat value with one team

The brief proposes one department or team with 5–10 people; the group is not yet selected. I would use that pilot to examine setup effort, review burden and voluntary return before arguing for wider adoption.

Still open: buyer and sponsor, rollout effort, support needs and commercial viability. No validated revenue or adoption results yet.

Pilot size is a proposal from the brief, not completed research. No confirmed budget, launch date or pricing decision was provided.

02 / THE WEB EXPERIENCEDESIGNING THE FIRST HANDOFF

Start with a task.
Stay close to the outcome.

The prototype explores a guided start: recognizable task suggestions, a review step before sending, and answers with sources. These screens make the hypothesis testable. They do not yet establish which task will be the most useful starting point for each employee.

A CLEAR FIRST STEP

Recognizable tasks give a newcomer something to react to. The current demo shows email, meeting follow-up and a document question. Research must establish which suggestions match the employee’s real work, and what they need before starting.

SCENARIO DISCOVERY / OPEN SET

Which task would you try first?

Email, meetings and knowledge are the current demo scenarios. Translation is another candidate. Start with employees’ actual work, then prioritize by frequency, review effort, perceived risk and willingness to repeat.

IN THE DEMO

Draft a reply

Help me respond to a thread without missing its context.

Test: is reviewing the draft easier than writing it?
IN THE DEMO

Follow up a meeting

Turn discussion into actions I can confirm and use.

Test: does the output fit the team’s follow-up routine?
IN THE DEMO

Find an answer

Help me check a rule against the relevant document.

Test: can I find and judge the supporting evidence?
TO EXPLORE

Translate for work

Prepare a Chinese–English draft with the right tone and terms.

Test: are meaning, terminology and review effort acceptable?

Also ask: what task is missing? The right entry point may be something employees bring to the study, beyond these four candidates.

INTERACTIVE PROTOTYPE

Meet your work companion.

Try a suggested task in the workspace below. Sample data, simulated responses, real interactions.

HKGAI Office Interactive demo

Loading the interactive workspace…

Home design from Figma, focused on task entry and the Sources setup panel; detailed approval and citation screens come from the product brief. Responses and connections are simulated. The current demo illustrates three scenarios; translation and reusable workflows are proposed areas for validation.

03 / THE INTERFACE DECISIONSTRUST THROUGH VISIBLE CONTROLS

A useful agent should
be easy to question.

To hand over real work, employees need to know what the agent can do, what it has used, and where their own judgment is required. The interface makes those boundaries visible. The research question is whether people understand and use them, especially when an answer looks convincing but is wrong.

01

Separate preparation from permission

The agent prepares an email; the employee controls the handoff. The review card offers send, edit and do-not-send paths. “Ask before action” stays visible. In a study, I would ask participants which parts of their own task they would delegate and observe what they actually check before approving.

PREPARE → REVIEW → APPROVE · Sending stays a separate action.
02

Let the reader check the answer

Source markers lead back to the relevant document. The proposed knowledge model separates personal, organization and official sources. A missing answer should stay explicit. Validation must test whether employees can spot a gap, challenge a citation and avoid accepting an unsupported answer.

ANSWER → EVIDENCE · A citation is a route back to the source.
03

Show what happened, and what comes next

The task-flow design keeps the plan, approval, progress and output together. It helps an employee see what was delegated and where they intervened. Follow-up suggestions offer a next step; research must establish whether that step fits the person’s real workflow.

PLAN → APPROVAL → OUTPUT · An interface proposal, shown with sample task data.
NEXT DESIGN HYPOTHESIS / NOT YET IMPLEMENTED

Teach the workflow, one approved detail at a time.

The longer-term question is how an agent becomes useful beyond its first answer. I would explore an explicit, editable way for employees to teach their process and decide what carries into the next task.

  1. 01

    Bring an example

    Start with a past output, template or real task. Identify the format, terminology and review steps that matter.

  2. 02

    Propose the routine

    The agent summarizes how to help: inputs, steps, output and approval boundary. The employee corrects the proposal.

  3. 03

    Choose what to reuse

    Ask before saving preferences. Let the employee inspect, edit or remove them and limit where they apply.

  4. 04

    Try the next task

    Show which preferences were applied. Compare correction effort and check that judgment stays with the employee.

This is a proposed interaction to test, not a claim that the current prototype automatically learns employees’ workflows.

04 / THE COMPANIONA CHARACTER WITH A JOB TO DO

Small colleague.
Always on the lookout.

A prairie dog stands up to keep watch and lives as part of a group. That became the agent’s visual metaphor: attentive, collaborative, and ready to take on a task. Its posture helps communicate what is happening. The character is a cue for attention and state; the product still has to earn trust through useful work and clear boundaries.

The prairie dog standing upright with a task slip and green scarf
ORDER RECEIVED

“I’m on it.”

Standing upright signals a transition into task work.

The prairie dog rests with its eyes closed beside the composer
ON STANDBY

Present, without demanding attention.

A quiet resting pose sits at the edge of the input area.

A small prairie-dog avatar with a green scarf
IN THE CONVERSATION

A recognizable face.

The head-only avatar gives agent replies a consistent identity.

01 · Resting02 · Attentive03 · Accepting a task04 · Working05 · Awaiting approval

Five states defined in the product brief. Posture supports the interface; explicit task labels and approval controls carry the meaning.

Yellow / #F5C543Cream / #FFF1BFForest / #144701Lime / #E4FF97
05 / THE VALIDATION PLANPROVE THE REASON TO EXIST

A useful first task.
Then a reason to return.

The open question is whether this approach earns a place in employees’ work. The next study should test the full journey: task choice, a first result, a decision to delegate, and a related task on another day.

PLANNED STUDY / NO RESULTS YET

Recruit government staff across roles and levels of agent experience. Ask them to bring representative, non-sensitive tasks and explain their existing process. Let them rank email, meetings, knowledge, translation and their own suggestions before selecting tasks for the study.

What would support—or challenge—the product direction?
QuestionHow to test itWhat to look for
01 / DIFFERENTIATIONWhy choose another tool?Compare a representative task in the employee’s current workflow and HKGAI Office. Where they already use WorkBuddy or another agent, include it and vary the order of the comparison.Prompting and setup effort, output usefulness, review burden and a concrete reason to use it again. If existing tools serve the task as well, narrow or rethink the proposition.
02 / FIRST TASKCan I find a place to start?Compare a blank composer with guided task suggestions. Let first-time users choose their own task without a moderator telling them what to ask.Task choice, time to a first useful result, requests for help and abandonment. Check which scenarios employees choose, including translation and tasks outside the demo.
03 / TRUSTDo I know what to hand over?Use safe sample outputs with a deliberate mistake or missing evidence. Ask participants to review, correct, decline or approve, and explain their boundary for delegation.Whether they catch the issue, inspect sources and understand what approval does. Confidence should track the quality of the result; a fast approval alone is not success.
04 / WORKFLOW FITDoes the next task get easier?In a later session, repeat a related task with an explicitly approved routine: format, tone, terminology and approval steps. Let the employee inspect, change or remove it.Repeated instructions, correction effort, inappropriate reuse and voluntary return. For translation, have a bilingual reviewer check meaning and terms as well as fluency.

What the prototype makes tangible

Guided task entry, review before action, source-linked answers and visible task progress. The bilingual demo and companion identity give participants something concrete to react to.

Explore the prototype ↗

What still needs to be learned

The strongest first scenario, the right delegation boundary and whether a reusable workflow earns repeat use. Translation and workflow learning are proposed directions. Real integrations and data-handling commitments also remain to be resolved.

THE DECISION THIS RESEARCH SHOULD ENABLE

Build around the tasks employees choose, can review, and want to repeat.

If one scenario earns that trust, start there. If review costs outweigh the help, or existing tools already meet the need, change the direction before expanding the feature set.